Papers › Distributional Reinforcement Learning with Quantile Regression

Distributional Reinforcement Learning with Quantile Regression

27 Oct 2017arXiv:1710.10044archive 2025-07-28

Will Dabney, Mark Rowland, Marc G. Bellemare, Rémi Munos

In reinforcement learning an agent interacts with the environment by taking actions and observing the next state and reward. When sampled probabilistically, these state transitions, rewards, and actions can all induce randomness in the observed long-term return. Traditionally, reinforcement learning algorithms average over this randomness to estimate the value function. In this paper, we build on recent work advocating a distributional approach to reinforcement learning in which the distribution over returns is modeled explicitly instead of only estimating the mean. That is, we examine methods of learning the value distribution instead of the value function. We give results that close a number of gaps between the theoretical and algorithmic results given by Bellemare, Dabney, and Munos (2017). First, we extend existing results to the approximate distribution setting. Second, we present a novel distributional reinforcement learning algorithm consistent with our theoretical formulation. Finally, we evaluate this new algorithm on the Atari 2600 games, observing that it significantly outperforms many of the recent improvements on DQN, including the related distributional algorithm C51.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 2 code samples harvested from 2 repositories linked to this paper: 2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code. Every run on this page is a failure of Syntology's instrument, not of the code.

By repository: community (archive-listed): 2 samples from 2 repositories, 2 ran (0 with no instrument failure; 2 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

No sample is linked to this paper from 5 of its repositories that Syntology harvested for other papers:

Levels written on 2026-09-22 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 1 of the 2 samples that ran has no recorded date.

17 repositories listed; official and paper-mentioned ones first.

Abdelhamid-bouzid/Distributional-RL mentioned on GitHubpytorchSyntology: not harvested report
Kchu/DeepRL_CK mentioned on GitHubpytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to QUOTA: The Quantile Option Architecture for Reinforcement Learning (arXiv:1811.02073; that paper's own run record: 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
ars-ashuha/quantile-regression-dqn-pytorch mentioned on GitHubpytorchMITSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
facebookresearch/Horizon mentioned on GitHubpytorchSyntology: not harvested report
facebookresearch/ReAgent mentioned on GitHubpytorchSyntology: not harvested report
ku2482/fqf-iqn-qrdqn.pytorch mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Fully Parameterized Quantile Function for Distributional Reinforcement Learning (arXiv:1911.02140; that paper's own run record: 6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified); nothing checks that they implement this paper's method. report
ku2482/rljax mentioned on GitHubjaxMITSyntology: not harvested report
marload/DistRL-TensorFlow2 mentioned on GitHubtfApache-2.0Syntology: not harvested report
marload/dist-rl-tf2 mentioned on GitHubtfApache-2.0Syntology: not harvested report
robinzixuan/IQN_Agent mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Fully Parameterized Quantile Function for Distributional Reinforcement Learning (arXiv:1911.02140; that paper's own run record: 6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified); nothing checks that they implement this paper's method. report
sannebh/riskaverse mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
sannebh/riskaverse_rl mentioned on GitHubpytorchSyntology: not harvested report
senya-ashukha/quantile-regression-dqn-pytorch mentioned on GitHubpytorchMITSyntology: not harvested report
DLR-RM/stable-baselines3 pytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Hyperparameter Trajectory Inference with Conditional Lagrangian Optimal Transport (arXiv:2603.01771; that paper's own run record: 6 ran (of which 1 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 1 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
SeungeonBaek/discrete-agents-test tfMITSyntology: not harvested report
ZiyiLiubird/DeepMARL-PyTorch pytorchSyntology: not harvested report
opendilab/DI-engine pytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Hindsight Experience Replay (arXiv:1707.01495; that paper's own run record: 16 ran (of which 10 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 0 violated, 10 with no contract checked; 5 where Syntology's instrument failed) · 0 unverified), Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context (arXiv:1901.02860; that paper's own run record: 67 ran (of which 37 constructed an object rather than computing a result; 49 with no instrument failure: 4 honoured, 1 violated, 44 with no contract checked; 18 where Syntology's instrument failed) · 76 unverified), Decision Transformer: Reinforcement Learning via Sequence Modeling (arXiv:2106.01345; that paper's own run record: 17 ran (of which 10 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 5 where Syntology's instrument failed) · 9 unverified) and 1 more (every one in this page's JSON twin); nothing checks that they implement this paper's method. report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

2 samples harvested: 2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Every run on this page is a failure of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · our draft was wrong
1ran; the contract check could not run

Licence: 2 of the 2 samples are pointer only, meaning Syntology does not serve that copy's text. For 1 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 2 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

ars-ashuha/quantile-regression-dqn-pytorch community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
huber in 13 papers rl_utils.py ran · our draft was wrong fingerprinted MIT (permissive) here; the stored copy is pointer only · c31cb0cb3f1f949f · report fixture: signature x:Tensor/2/float, k:float/0/float · returned Tensor · level recorded, date not recorded
sannebh/riskaverse community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
behaviour_policy risk_strategies.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted no licence file found · pointer only · 868da5f8ecd37cb8 · report fixture: signature dist:ndarray/3/float, behaviour_p:str/0/str, quant:float/0/float, const:int/0/int · returned ndarray · level recorded 2026-09-22

Tasks

Atari GamesDistributional Reinforcement LearningReinforcement LearningReinforcement Learning (RL)quantile regressionregressionreinforcement-learning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Atari Games Atari 2600 Alien QR-DQN-1 Score 4871 #19 of 49 Archive leaderboard report
Atari Games Atari 2600 Amidar QR-DQN-1 Score 1641 #15 of 48 Archive leaderboard report
Atari Games Atari 2600 Assault QR-DQN-1 Score 22012 #10 of 45 Archive leaderboard report
Atari Games Atari 2600 Asterix QR-DQN-1 Score 261025 #18 of 49 Archive leaderboard report
Atari Games Atari 2600 Asteroids QR-DQN-1 Score 4226 #17 of 43 Archive leaderboard report
Atari Games Atari 2600 Atlantis QR-DQN-1 Score 971850 #15 of 42 Archive leaderboard report
Atari Games Atari 2600 Bank Heist QR-DQN-1 Score 1249 #15 of 45 Archive leaderboard report
Atari Games Atari 2600 Battle Zone QR-DQN-1 Score 39268 #15 of 47 Archive leaderboard report
Atari Games Atari 2600 Beam Rider QR-DQN-1 Score 34821 #11 of 49 Archive leaderboard report
Atari Games Atari 2600 Berzerk QR-DQN-1 Score 3117 #12 of 39 Archive leaderboard report
Atari Games Atari 2600 Bowling QR-DQN-1 Score 77.2 #17 of 44 Archive leaderboard report
Atari Games Atari 2600 Boxing QR-DQN-1 Score 99.9 #11 of 45 Archive leaderboard report
Atari Games Atari 2600 Breakout QR-DQN-1 Score 742 #14 of 58 Archive leaderboard report
Atari Games Atari 2600 Centipede QR-DQN-1 Score 12447 #15 of 45 Archive leaderboard report
Atari Games Atari 2600 Chopper Command QR-DQN-1 Score 14667 #16 of 45 Archive leaderboard report
Atari Games Atari 2600 Crazy Climber QR-DQN-1 Score 161196 #16 of 49 Archive leaderboard report
Atari Games Atari 2600 Defender QR-DQN-1 Score 47887 #14 of 21 Archive leaderboard report
Atari Games Atari 2600 Demon Attack QR-DQN-1 Score 121551 #13 of 46 Archive leaderboard report
Atari Games Atari 2600 Double Dunk QR-DQN-1 Score 21.9 #11 of 43 Archive leaderboard report
Atari Games Atari 2600 Enduro QR-DQN-1 Score 2355 #10 of 48 Archive leaderboard report
Atari Games Atari 2600 Fishing Derby QR-DQN-1 Score 39 #19 of 44 Archive leaderboard report
Atari Games Atari 2600 Freeway QR-DQN-1 Score 34 #4 of 59 Archive leaderboard report
Atari Games Atari 2600 Frostbite QR-DQN-1 Score 4384 #17 of 53 Archive leaderboard report
Atari Games Atari 2600 Gopher QR-DQN-1 Score 113585 #9 of 43 Archive leaderboard report
Atari Games Atari 2600 Gravitar QR-DQN-1 Score 995 #23 of 53 Archive leaderboard report
Atari Games Atari 2600 HERO QR-DQN-1 Score 21395 #24 of 44 Archive leaderboard report
Atari Games Atari 2600 Ice Hockey QR-DQN-1 Score -1.7 #39 of 43 Archive leaderboard report
Atari Games Atari 2600 James Bond QR-DQN-1 Score 4703 #15 of 45 Archive leaderboard report
Atari Games Atari 2600 Kangaroo QR-DQN-1 Score 15356 #5 of 47 Archive leaderboard report
Atari Games Atari 2600 Krull QR-DQN-1 Score 11447 #12 of 45 Archive leaderboard report
Atari Games Atari 2600 Kung-Fu Master QR-DQN-1 Score 76642 #12 of 43 Archive leaderboard report
Atari Games Atari 2600 Montezuma's Revenge QR-DQN-1 Score 0 #47 of 50 Archive leaderboard report
Atari Games Atari 2600 Ms. Pacman QR-DQN-1 Score 5821 #17 of 47 Archive leaderboard report
Atari Games Atari 2600 Name This Game QR-DQN-1 Score 21890 #10 of 43 Archive leaderboard report
Atari Games Atari 2600 Phoenix QR-DQN-1 Score 16585 #17 of 21 Archive leaderboard report
Atari Games Atari 2600 Pitfall! QR-DQN-1 Score 0 #11 of 23 Archive leaderboard report
Atari Games Atari 2600 Pong QR-DQN-1 Score 21 #8 of 52 Archive leaderboard report
Atari Games Atari 2600 Private Eye QR-DQN-1 Score 350 #27 of 52 Archive leaderboard report
Atari Games Atari 2600 Q*Bert QR-DQN-1 Score 572510 #2 of 57 Archive leaderboard report
Atari Games Atari 2600 River Raid QR-DQN-1 Score 17571 #14 of 41 Archive leaderboard report
Atari Games Atari 2600 Road Runner QR-DQN-1 Score 64262 #13 of 44 Archive leaderboard report
Atari Games Atari 2600 Robotank QR-DQN-1 Score 59.4 #24 of 42 Archive leaderboard report
Atari Games Atari 2600 Seaquest QR-DQN-1 Score 8268 #25 of 57 Archive leaderboard report
Atari Games Atari 2600 Skiing QR-DQN-1 Score -9324 #10 of 23 Archive leaderboard report
Atari Games Atari 2600 Solaris QR-DQN-1 Score 6740 #11 of 23 Archive leaderboard report
Atari Games Atari 2600 Space Invaders QR-DQN-1 Score 20972 #14 of 55 Archive leaderboard report
Atari Games Atari 2600 Star Gunner QR-DQN-1 Score 77495 #19 of 43 Archive leaderboard report
Atari Games Atari 2600 Surround QR-DQN-1 Score 8.2 #7 of 15 Archive leaderboard report
Atari Games Atari 2600 Tennis QR-DQN-1 Score 23.6 #7 of 43 Archive leaderboard report
Atari Games Atari 2600 Time Pilot QR-DQN-1 Score 10345 #23 of 44 Archive leaderboard report
Atari Games Atari 2600 Tutankham QR-DQN-1 Score 297 #9 of 44 Archive leaderboard report
Atari Games Atari 2600 Up and Down QR-DQN-1 Score 71260 #18 of 44 Archive leaderboard report
Atari Games Atari 2600 Venture QR-DQN-1 Score 43.9 #39 of 55 Archive leaderboard report
Atari Games Atari 2600 Video Pinball QR-DQN-1 Score 705662 #10 of 42 Archive leaderboard report
Atari Games Atari 2600 Wizard of Wor QR-DQN-1 Score 25061 #11 of 41 Archive leaderboard report
Atari Games Atari 2600 Yars Revenge QR-DQN-1 Score 26447 #16 of 17 Archive leaderboard report
Atari Games Atari 2600 Zaxxon QR-DQN-1 Score 13112 #20 of 41 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

ConvolutionDQNDense ConnectionsQ-Learning

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections